{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:32:49Z","timestamp":1743125569746,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031207150"},{"type":"electronic","value":"9783031207167"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20716-7_10","type":"book-chapter","created":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T05:03:02Z","timestamp":1670562182000},"page":"119-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Saliency Can Be All You Need in\u00a0Contrastive Self-supervised Learning"],"prefix":"10.1007","author":[{"given":"Veysel","family":"Kocaman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ofer M.","family":"Shir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"B\u00e4ck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed Nabil","family":"Belbachir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,10]]},"reference":[{"key":"10_CR1","series-title":"Advances in Computer Vision and Pattern Recognition","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-42128-1","volume-title":"Unsupervised Learning in Space and Time","author":"M Leordeanu","year":"2020","unstructured":"Leordeanu, M.: Unsupervised Learning in Space and Time. ACVPR, Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-42128-1"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Schmid, C., Sminchisescu, C.: Self-supervised learning with geometric constraints in monocular video: connecting flow, depth, and camera. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7063\u20137072 (2019)","DOI":"10.1109\/ICCV.2019.00716"},{"issue":"1","key":"10_CR3","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/technologies9010002","volume":"9","author":"A Jaiswal","year":"2020","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., Makedon, F.: A survey on contrastive self-supervised learning. Technologies 9(1), 2 (2020)","journal-title":"Technologies"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Ciga, O., Martel, A.L.: Learning to segment images with classification labels. Med. Image Anal. 68, 101912 (2021)","DOI":"10.1016\/j.media.2020.101912"},{"key":"10_CR5","unstructured":"Liu, X., et al.: Generative or contrastive. IEEE Trans. Knowl. Data Eng. Self-supervised Learn. (2021)"},{"key":"10_CR6","unstructured":"Cheng, M., Zhang, G., Niloy J, et al.: Global contrast based salient region detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Spring, USA, pp. 409\u2013416 (2011)"},{"key":"10_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"issue":"4","key":"10_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925974","volume":"35","author":"S Iizuka","year":"2016","unstructured":"Iizuka, S., Simo-Serra, E., Ishikawa, H.: Let there be color! joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification. ACM Trans. Graph. (ToG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"10_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/978-3-319-46493-0_35","volume-title":"Computer Vision","author":"G Larsson","year":"2016","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 577\u2013593. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_35"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10_CR12","unstructured":"Lee, D.-H., et al.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3, p. 896 (2013)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.-T., Hovy, E., Le, Q.V.: Self-training with noisy student improves imagenet classification. arxiv e-prints, art. arXiv preprint arXiv:1911.04252 (2019)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"10_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Afouras, T., Asano, Y.M., Fagan, F., Vedaldi, A., Metze, F.: Self-supervised object detection from audio-visual correspondence. arXiv preprintarXiv:2104.06401 (2021)","DOI":"10.1109\/CVPR52688.2022.01032"},{"key":"10_CR18","unstructured":"Dhere, A., Sivaswamy, J.: Self-supervised learning for segmentation. arXiv preprintarXiv:2101.05456 (2021)"},{"key":"10_CR19","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10_CR21","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprintarXiv:2003.04297 (2020a)"},{"key":"10_CR22","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill, J.-B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10_CR23","unstructured":"Nakamura, H., Okada, M., Taniguchi, T.: Self-supervised representation learning as multimodal variational inference. arXiv preprintarXiv:2203.11437 (2022)"},{"key":"10_CR24","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. Adv. Neural Inf. Process. Syst. 33, 22243\u201322255 (2020b)"},{"key":"10_CR25","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020c)"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1920\u20131929 (2019)","DOI":"10.1109\/CVPR.2019.00202"},{"key":"10_CR27","unstructured":"Balestriero, R., Bottou, L., LeCun, Y.: The effects of regularization and data augmentation are class dependent. arXiv preprintarXiv:2204.03632 (2022)"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: \u201cgrabcut\u201d interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23(3), 309\u2013314 (2004)","DOI":"10.1145\/1015706.1015720"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Everingham, M., Gool, L.V., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9865\u20139874 (2019)","DOI":"10.1109\/ICCV.2019.00996"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Kanezaki, A.: Unsupervised image segmentation by backpropagation. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1543\u20131547. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462533"},{"key":"10_CR32","doi-asserted-by":"publisher","first-page":"8055","DOI":"10.1109\/TIP.2020.3011269","volume":"29","author":"W Kim","year":"2020","unstructured":"Kim, W., Kanezaki, A., Tanaka, M.: Unsupervised learning of image segmentation based on differentiable feature clustering. IEEE Trans. Image Process. 29, 8055\u20138068 (2020)","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"10_CR33","doi-asserted-by":"publisher","first-page":"5389","DOI":"10.5194\/essd-13-5389-2021","volume":"13","author":"H Jiang","year":"2021","unstructured":"Jiang, H., et al.: Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery. Earth Syst. Sci. Data 13(11), 5389\u20135401 (2021)","journal-title":"Earth Syst. Sci. Data"},{"key":"10_CR34","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"key":"10_CR35","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223. JMLR Workshop and Conference Proceedings (2011)"},{"key":"10_CR36","unstructured":"Hamilton, M., Zhang, Z., Hariharan, B., Snavely, N., Freeman, W.T.: Unsupervised semantic segmentation by distilling feature correspondences. arXiv preprint arXiv:2203.08414 (2022)"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. arXiv preprint arXiv:2201.02605 (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"10_CR39","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny., S.: Barlow twins: self-supervised learning via redundancy reduction. In: International Conference on Machine Learning, pp. 12310\u201312320. PMLR (2021)"},{"key":"10_CR40","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W-Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Cole, E., Yang, X., Wilber, K., Mac Aodha, O., Belongie, S.: When does contrastive visual representation learning work? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14755\u201314764 (2022)","DOI":"10.1109\/CVPR52688.2022.01434"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20716-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T05:05:01Z","timestamp":1670562301000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20716-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031207150","9783031207167"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20716-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Diego, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"110","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"61","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"55% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2-3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}